Learning ontology rules for semantic video annotation

Abstract

Semantic video annotation using ontologies has received a large attention from the scientific community in the recent years. Ontologies are being regarded as an appropriate tool to bridge the semantic gap. In this paper we present an overview of the state-of-the-art of approaches and algorithms that exploit ontologies to perform semantic video annotation and present an approach to automatically learn rules describing high-level concepts. This approach exploits the domain knowledge embedded into an ontology to learn a set of rules for semantic video annotation. The proposed technique is an adaptation of the First Order Inductive Learner (FOIL) technique to the Semantic Web Rule Language (SWRL) standard: Experiments have been performed in two different video domains: i) the TRECVID 2005 broadcast news collection, to detect events related to airplanes, such as taxiing, flying, landing and taking off; ii) surveillance videos, to detect if a person enters or exits a specific area. The promising experimental performance demonstrates the effectiveness and flexibility of the proposed framework

Extensible Hierarchical Method of Detecting Interactive Actions for Video Understanding

“…There have been some efforts made to recognize video events by making use of ontologies and rules represented by the World Wide Web (W3C) standards including the Ontology Web Language (OWL) and Semantic Web Rule Language (SWRL) , or other ontology‐based formalisms. Although the ontology‐based studies have dealt with how to learn rules automatically for composite events in a video , , they have fixed atomic events in advance, which compose rules for composite events. However, it is difficult to define all necessary atomic events in advance in the real world.…”

Commonsense Knowledge for the Collection of Ground Truth Data on Semantic Descriptors

“…Semantic annotation can be performed manually, by associating the terms of the ontology to the individual elements of the video, or automatically, by exploiting results and developments in pattern recognition and image/video analysis [8]- [10]. However, these approaches generally manage very few concepts, because of the inability to automatically recognize a wide range of elements from videos.…”

Automatic semantic video annotation in wide domain videos based on similarity and commonsense knowledgebases

“…A good SVM shots classifier, based on motion feature alone, was suggested in [4]. Bertini et al [12] have built a system that learns events rules from Ontology. Others, like in [13], use association mining techniques to indicate the existence of one high-level concept from the simultaneously existence of other concepts, trying to enhance accuracy of semantic concepts detection.…”